_ Git - youtube-dl/blob - youtube_dl/extractor/francetv.py

   1 # encoding: utf-8
   2 import re
   3 import xml.etree.ElementTree
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urlparse,
   8 )
   9
  10
  11 class PluzzIE(InfoExtractor):
  12     IE_NAME = u'pluzz.francetv.fr'
  13     _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
  14
  15     _TEST = {
  16         u'url': u'http://pluzz.francetv.fr/videos/allo_rufo_saison5_,88439064.html',
  17         u'file': u'88439064.mp4',
  18         u'info_dict': {
  19             u'title': u'Allô Rufo',
  20             u'description': u'md5:d909f1ebdf963814b65772aea250400e',
  21         },
  22         u'params': {
  23             u'skip_download': True,
  24         },
  25     }
  26
  27     def _real_extract(self, url):
  28         title = re.match(self._VALID_URL, url).group(1)
  29         webpage = self._download_webpage(url, title)
  30         video_id = self._search_regex(
  31             r'data-diffusion="(\d+)"', webpage, 'ID')
  32
  33         xml_desc = self._download_webpage(
  34             'http://www.pluzz.fr/appftv/webservices/video/'
  35             'getInfosOeuvre.php?id-diffusion='
  36             + video_id, title, 'Downloading XML config')
  37         info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8'))
  38
  39         manifest_url = info.find('videos/video/url').text
  40         video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
  41         video_url = video_url.replace('/z/', '/i/')
  42         thumbnail_path = info.find('image').text
  43
  44         return {'id': video_id,
  45                 'ext': 'mp4',
  46                 'url': video_url,
  47                 'title': info.find('titre').text,
  48                 'thumbnail': compat_urlparse.urljoin(url, thumbnail_path),
  49                 'description': info.find('synopsis').text,
  50                 }